UFB
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Preference Alignment | UFB | Win Rate83.2 | 32 | |
| Preference Alignment | UFB (test) | Win Rate81.05 | 18 | |
| Reward Model Learning | UFB | Win Rate72.5 | 10 |
Showing 3 of 3 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Preference Alignment | UFB | Win Rate83.2 | 32 | |
| Preference Alignment | UFB (test) | Win Rate81.05 | 18 | |
| Reward Model Learning | UFB | Win Rate72.5 | 10 |